Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9950
    Prev
    Next
    INDEX
    Explanations

    words related to television ratings

    oai_token-act-pair · gpt-3.5-turbo

    references to television ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alz
    -0.87
    working
    -0.76
     Fathers
    -0.70
    vas
    -0.67
     Remem
    -0.67
     Marse
    -0.67
     Gibbs
    -0.65
    forth
    -0.65
    cise
    -0.65
    adr
    -0.64
    POSITIVE LOGITS
     ratings
    1.41
     rating
    1.23
     Ratings
    1.18
     Rating
    0.95
     rated
    0.92
     veter
    0.91
     coefficients
    0.83
    omial
    0.82
    olitan
    0.80
    Rating
    0.78
    Activations Density 0.007%

    No Known Activations